Yang, W., Xie, L., Cai, J., Yan, Y., Dai, H.-N., & Wang, H. (2026). Talk2Code: A Multi-Turn Interaction Benchmark with Dual-Track Evaluation for Code Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34331–34339. https://doi.org/10.1609/aaai.v40i40.40730